© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 21-GEMMASCOPE-RES-16K
    11. 14742
    Prev
    Next
    INDEX
    Explanations

    function definitions and control structures, particularly in programming code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ochem
    -0.54
     nó
    -0.45
    isma
    -0.43
    an
    -0.42
    atro
    -0.41
    esos
    -0.41
    zkiem
    -0.40
    рованные
    -0.39
     trop
    -0.39
    cionar
    -0.39
    POSITIVE LOGITS
     self
    3.22
    self
    3.15
     Self
    2.42
    Self
    2.31
     SELF
    2.16
     selves
    1.96
    SELF
    1.85
     Selbst
    1.84
     herself
    1.74
     zelf
    1.69
    Activations Density 0.054%

    No Known Activations